Upload 8 files
Browse files- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +67 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ad805309eddf0fc5483bf2717a7304f8d18b46786094c3f455821c27235fb6a
|
| 3 |
+
size 686563322
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28fcdac32fbc25295ab8c950f93b8c6462148515f6b88cd4dd6308c4b390d487
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6ed8aa2006c9b59e429335f63b8eafa7f5e201e7b2961d3c0955297c258416f
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.04190065711736679,
|
| 3 |
+
"best_model_checkpoint": "ai_vs_real_image_detection/checkpoint-2252",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2252,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.44404973357015987,
|
| 13 |
+
"grad_norm": 1.6082425117492676,
|
| 14 |
+
"learning_rate": 7.956403269754768e-07,
|
| 15 |
+
"loss": 0.0398,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8880994671403197,
|
| 20 |
+
"grad_norm": 4.518634796142578,
|
| 21 |
+
"learning_rate": 5.685740236148955e-07,
|
| 22 |
+
"loss": 0.038,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_accuracy": 0.9844924127307925,
|
| 28 |
+
"eval_loss": 0.043014705181121826,
|
| 29 |
+
"eval_runtime": 698.9147,
|
| 30 |
+
"eval_samples_per_second": 68.737,
|
| 31 |
+
"eval_steps_per_second": 2.149,
|
| 32 |
+
"step": 1126
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.3321492007104796,
|
| 36 |
+
"grad_norm": 7.5788960456848145,
|
| 37 |
+
"learning_rate": 3.415077202543142e-07,
|
| 38 |
+
"loss": 0.0364,
|
| 39 |
+
"step": 1500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.7761989342806395,
|
| 43 |
+
"grad_norm": 2.462517499923706,
|
| 44 |
+
"learning_rate": 1.1444141689373296e-07,
|
| 45 |
+
"loss": 0.0375,
|
| 46 |
+
"step": 2000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.0,
|
| 50 |
+
"eval_accuracy": 0.9848670926916592,
|
| 51 |
+
"eval_loss": 0.04190065711736679,
|
| 52 |
+
"eval_runtime": 790.7788,
|
| 53 |
+
"eval_samples_per_second": 60.752,
|
| 54 |
+
"eval_steps_per_second": 1.899,
|
| 55 |
+
"step": 2252
|
| 56 |
+
}
|
| 57 |
+
],
|
| 58 |
+
"logging_steps": 500,
|
| 59 |
+
"max_steps": 2252,
|
| 60 |
+
"num_input_tokens_seen": 0,
|
| 61 |
+
"num_train_epochs": 2,
|
| 62 |
+
"save_steps": 500,
|
| 63 |
+
"total_flos": 1.1168300527234228e+19,
|
| 64 |
+
"train_batch_size": 64,
|
| 65 |
+
"trial_name": null,
|
| 66 |
+
"trial_params": null
|
| 67 |
+
}
|